README.md

---
license: apache-2.0
datasets:
- IAmSkyDra/HCMUT_FAQ
language:
- vi
tags:
- education
- text-generation-inference
- gemma
- llama-factory
- unsloth
widget:
- text: Chào bạn
  output:
    text: >-
      Chào bạn! Tôi là GemSUra-edu, một trợ lý AI được phát triển bởi Long
      Nguyen.
  example_title: Query 1

- text: Hiệu trưởng hiện tại của trường Đại học Bách Khoa
  output:
    text: >-
      Hiệu trưởng hiện tại của trường Đại học Bách Khoa là PGS. TS. Mai Thanh Phong.
  example_title: Query 2

- text: OISP là viết tắt của
  output:
    text: >-
      Văn phòng Đào tạo Quốc tế (Office for International Study Programs)
  example_title: Query 3
---
## Introduction

GemSUra-edu is a large language model fine-tuned on a dataset of FAQs from HCMUT, based on the pre-trained model [GemSUra 2B](https://huggingface.co/ura-hcmut/GemSUra-2B) developed by the URA research group at Ho Chi Minh City University of Technology (HCMUT).

## Inference (with Unsloth for higher speed)

```python
from unsloth import FastLanguageModel
import torch

# Load model and tokenizer
model, tokenizer = FastLanguageModel.from_pretrained(
    model_name="IAmSkyDra/GemSUra-edu",
    max_seq_length=4096,
    dtype=None,
    load_in_4bit=True
)

FastLanguageModel.for_inference(model)

query_template = "<start_of_turn>user\n{query}<end_of_turn>\n<start_of_turn>model\n"

while True:
    query = input("Query: ")
    if query.lower() == "exit":
        break

    query = query_template.format(query=query)
    inputs = tokenizer(query, return_tensors="pt")

    outputs = model.generate(**inputs, max_new_tokens=4096, use_cache=True)
    generated_text = tokenizer.batch_decode(outputs, skip_special_tokens=True)
    answer = generated_text[0].split("model\n")[1].strip()
    print(answer)
```

## Inference (with Transformers)

```python
import transformers
from transformers import AutoModelForCausalLM, AutoTokenizer

pipeline_kwargs = {
    "temperature": 0.1,
    "max_new_tokens": 4096,
    "do_sample": True
}

if __name__ == "__main__":
    # Load model
    model = AutoModelForCausalLM.from_pretrained(
        "IAmSkyDra/GemSUra-edu",
        device_map="auto"
    )
    model.eval()

    # Load tokenizer
    tokenizer = AutoTokenizer.from_pretrained(
        "IAmSkyDra/GemSUra-edu",
        trust_remote_code=True
    )

    pipeline = transformers.pipeline(
        model=model,
        tokenizer=tokenizer,
        return_full_text=False,
        task='text-generation',
        **pipeline_kwargs
    )

    query_template = "<start_of_turn>user\n{query}<end_of_turn>\n<start_of_turn>model\n"

    while True:
        query = input("Query: ")
        if query.lower() == "exit":
            break

        query = query_template.format(query=query)
        answer = pipeline(query)[0]["generated_text"]
        answer = answer.split("model\n")[1].strip()
        print(answer)
```

## Notation

If you want to quantize the model for deployment on local devices, it should be quantized to at least 8 bits.